Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.8794. Min Act: -0.1700
Data Index: 5114839 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6919. Min Act: -0.1699
Data Index: 3471363 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 759031 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6294. Min Act: -0.1700
Data Index: 1799216 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6294. Min Act: -0.1700
Data Index: 6141970 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6294. Min Act: -0.1700
Data Index: 5967221 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5356. Min Act: -0.1700
Data Index: 101431 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5356. Min Act: -0.1700
Data Index: 6385885 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5669. Min Act: -0.1700
Data Index: 6925291 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5044. Min Act: -0.1700
Data Index: 1658344 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5669. Min Act: -0.1700
Data Index: 2742007 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5044. Min Act: -0.1700
Data Index: 5424063 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5356. Min Act: -0.1700
Data Index: 4218701 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5044. Min Act: -0.1700
Data Index: 3407492 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.4731. Min Act: -0.1700
Data Index: 3165325 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.5044. Min Act: -0.1700
Data Index: 1663137 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.4419. Min Act: -0.1700
Data Index: 1953376 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.4419. Min Act: -0.1700
Data Index: 3952476 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.4731. Min Act: -0.1700
Data Index: 1536113 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.4106. Min Act: -0.1700
Data Index: 1368028 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19